List of material on Classification: September 8, 2009 1. Classification: what and why needed. 2. Classification is a two-step process 3. Supervised and unsupervised learning 4. Issues / criteria for selecting classifiers 5. Decision (classification) tree (DT): how it works; how to build (we cover Quinlan’s algorithm); illustrative example; some related issues 6. Classification model evaluation: (Performance assessment: Training, validation, test / generalization errors Holdout method (training, validation, test sets) Cross-validation 7. Case studies using RBF classifiers (details of RBF classifiers will be discussed later): Cancer class determination(microarray data analysis), Pima Indians diabetes classification, Soybean disease classification; (Software)module criticality assessment